python爬蟲案例：使用XPath爬網頁圖片

用XPath來做一個簡單的爬蟲，嘗試爬取某個貼吧里的所有帖子，並且將該這個帖子里每個樓層發布的圖片下載到本地。

# -*- coding:utf-8 -*-

import urllib
import urllib2
from lxml import etree


def loadPage(url):
    """
        作用：根據url發送請求，獲取服務器響應文件
        url: 需要爬取的url地址
    """
    #print url
    #headers = {"User-Agent" : "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.56 Safari/535.11"}

    request = urllib2.Request(url)
    html = urllib2.urlopen(request).read()
    # 解析HTML文檔為HTML DOM模型
    content = etree.HTML(html)
    #print content
    # 返回所有匹配成功的列表集合
    link_list = content.xpath('//div[@class="t_con cleafix"]/div/div/div/a/@href')

    #link_list = content.xpath('//a[@class="j_th_tit"]/@href')
    for link in link_list:
        fulllink = "http://tieba.baidu.com" + link
        # 組合為每個帖子的鏈接
        #print link
        loadImage(fulllink)


# 取出每個帖子里的每個圖片連接
def loadImage(link):
    headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
    request = urllib2.Request(link, headers = headers)
    html = urllib2.urlopen(request).read()
    # 解析
    content = etree.HTML(html)
    # 取出帖子里每層層主發送的圖片連接集合
    #link_list = content.xpath('//img[@class="BDE_Image"]/@src')
    # link_list = content.xpath('//div[@class="post_bubble_middle"]')
    link_list = content.xpath('//img[@class="BDE_Image"]/@src')
    # 取出每個圖片的連接
    for link in link_list:
        # print link
        writeImage(link)


def writeImage(link):
    """
        作用：將html內容寫入到本地
        link：圖片連接
    """
    #print "正在保存 " + filename
    headers = {"User-Agent" : "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36"}
    # 文件寫入
    request = urllib2.Request(link, headers = headers)
    # 圖片原始數據
    image = urllib2.urlopen(request).read()
    # 取出連接后10位做為文件名
    filename = link[-10:]
    # 寫入到本地磁盤文件內
    with open(filename, "wb") as f:
        f.write(image)
    print "已經成功下載 "+ filename

def tiebaSpider(url, beginPage, endPage):
    """
        作用：貼吧爬蟲調度器，負責組合處理每個頁面的url
        url : 貼吧url的前部分
        beginPage : 起始頁
        endPage : 結束頁
    """
    for page in range(beginPage, endPage + 1):
        pn = (page - 1) * 50
        #filename = "第" + str(page) + "頁.html"
        fullurl = url + "&pn=" + str(pn)
        #print fullurl
        loadPage(fullurl)
        #print html

        print "謝謝使用"

if __name__ == "__main__":
    kw = raw_input("請輸入需要爬取的貼吧名:")
    beginPage = int(raw_input("請輸入起始頁："))
    endPage = int(raw_input("請輸入結束頁："))

    url = "http://tieba.baidu.com/f?"
    key = urllib.urlencode({"kw": kw})
    fullurl = url + key
    tiebaSpider(fullurl, beginPage, endPage)

效果：